List Models

List all available AI models with their pricing information. No payment required.

Endpoint


GET /v1/models

Request

No parameters required.

Response

Success (200 OK)


{
  total: number;
  models: Array<{
    id: string;                    // Model identifier
    name: string;                  // Human-readable model name
    description: string;           // Model description
    context_length: number;        // Maximum context window in tokens
    pricing: {
      input_per_1k_tokens: number;   // Cost per 1K input tokens (USD)
      output_per_1k_tokens: number;  // Cost per 1K output tokens (USD)
      blended_per_1k_tokens: number; // Average cost per 1K tokens (USD)
    }
  }>
}

Examples

Basic Request


curl https://api.x-router.ai/v1/models

With JavaScript


const response = await fetch('https://api.x-router.ai/v1/models');
const data = await response.json();
 
console.log(`Total models: ${data.total}`);
console.log('Available models:');
 
data.models.forEach(model => {
  console.log(`- ${model.id}: ${model.name}`);
});

Find Cheapest Model


const response = await fetch('https://api.x-router.ai/v1/models');
const data = await response.json();
 
const cheapest = data.models.reduce((min, model) =>
  model.pricing.blended_per_1k_tokens < min.pricing.blended_per_1k_tokens
    ? model
    : min
);
 
console.log(`Cheapest model: ${cheapest.id}`);
console.log(`Cost: $${cheapest.pricing.blended_per_1k_tokens} per 1K tokens`);

Filter by Provider


const response = await fetch('https://api.x-router.ai/v1/models');
const data = await response.json();
 
// Get all Anthropic models
const anthropicModels = data.models.filter(m => m.id.startsWith('anthropic/'));
 
console.log('Anthropic models:');
anthropicModels.forEach(model => {
  console.log(`- ${model.name}: $${model.pricing.blended_per_1k_tokens}/1K tokens`);
});

Compare Pricing


const response = await fetch('https://api.x-router.ai/v1/models');
const data = await response.json();
 
const models = ['anthropic/claude-3.5-sonnet', 'openai/gpt-4o', 'google/gemini-pro'];
 
console.log('Pricing comparison:');
models.forEach(modelId => {
  const model = data.models.find(m => m.id === modelId);
  if (model) {
    console.log(`${model.name}:`);
    console.log(`  Input: $${model.pricing.input_per_1k_tokens}/1K`);
    console.log(`  Output: $${model.pricing.output_per_1k_tokens}/1K`);
    console.log(`  Blended: $${model.pricing.blended_per_1k_tokens}/1K`);
  }
});

Example Response


{
  "total": 295,
  "models": [
    {
      "id": "anthropic/claude-3.5-sonnet",
      "name": "Claude 3.5 Sonnet",
      "description": "Anthropic's most intelligent model",
      "context_length": 200000,
      "pricing": {
        "input_per_1k_tokens": 0.003,
        "output_per_1k_tokens": 0.015,
        "blended_per_1k_tokens": 0.009
      }
    },
    {
      "id": "openai/gpt-4o",
      "name": "GPT-4o",
      "description": "OpenAI's high-intelligence flagship model",
      "context_length": 128000,
      "pricing": {
        "input_per_1k_tokens": 0.0025,
        "output_per_1k_tokens": 0.01,
        "blended_per_1k_tokens": 0.00625
      }
    },
    {
      "id": "google/gemini-pro",
      "name": "Gemini Pro",
      "description": "Google's advanced AI model",
      "context_length": 32000,
      "pricing": {
        "input_per_1k_tokens": 0.000125,
        "output_per_1k_tokens": 0.000375,
        "blended_per_1k_tokens": 0.00025
      }
    }
  ]
}

Model Providers

X-Router provides access to models from many providers including:

Anthropic: Claude 3.5 Sonnet, Claude 3 Opus, Claude 3 Haiku
OpenAI: GPT-4o, GPT-4 Turbo, GPT-3.5 Turbo
Google: Gemini Pro, Gemini Ultra
Meta: Llama 3, Llama 2
Mistral: Mistral Large, Mistral Medium
Cohere: Command R+, Command
And many more…

The model list is updated regularly. Use this endpoint to get the current list.

Using Models

To use a model, pass its id in the model parameter of the Chat Completions endpoint:


const response = await fetchWithPayment('https://api.x-router.ai/v1/chat/completions', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    messages: [{ role: 'user', content: 'Hello!' }],
    model: 'anthropic/claude-3.5-sonnet',  // Use model ID from /v1/models
    max_tokens: 100
  })
});

Pricing Information

The pricing object contains three fields:

input_per_1k_tokens: Cost per 1,000 input tokens (your messages)
output_per_1k_tokens: Cost per 1,000 output tokens (AI response)
blended_per_1k_tokens: Average cost assuming 50/50 input/output split

Use these values to estimate costs for your use case. For exact cost estimates, use the Estimate endpoint.